Generate Human Design Report (PDF or HTML)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only give the generic write/open-world/idempotent profile; the description adds the material fact that each call costs 5,000 credits (~50% of a free monthly budget) and should be user-confirmed. It still doesn't say whether a repeat call re-charges, where the file is delivered, or what format is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The payload contents are front-loaded in a single dense line, followed by compact bracketed metadata for group, endpoint, required field and cost. No filler; the only quibble is that the contents list crowds out the more decision-relevant cost/format information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is not owed, and the cost warning is a genuine addition. But an expensive report generator that omits the output format (PDF vs HTML) and the language/whitelabel options leaves real gaps for a tool whose main job is producing a customizable document.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 33%, the description needs to carry weight, but it only restates '[Required: chart]'. The other two parameters (language with its 21-value enum, and the large whitelabel object) get no mention and are entirely undescribed in the schema either, so the agent learns nothing about them from either source.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates exactly what the generated document contains (Type, Strategy, Authority, Profile, Definition, Not-Self, Incarnation Cross, 9 centers, channels), which makes the artifact concrete. It stops short of a verb-led statement and never mentions the PDF-vs-HTML choice advertised in the title, nor distinguishes itself from the sibling astroway_hd_human_design that returns the same underlying data as JSON.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Confirm with user before invoking' plus the credit cost is a real, actionable invocation guardrail that most definitions lack. However, there is no guidance on when to choose this over astroway_hd_human_design (raw data) or the other astroway_reports_* variants, so the alternative-selection decision is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.